PTplanner: Efficient Autonomous UAV Exploration via Prior-Enhanced and Topology-Aware Hierarchical Planning

Highlights: What are the main findings? This work proposes a hierarchical exploration planning framework that fully leverages real-time acquired prior knowledge to enhance exploration efficiency, while still outperforming existing state-of-the-art algorithms even in the absence of prior knowledge. This work presents a CTSP-based local coverage planning approach to generate highly efficient local coverage viewpoint sequences, substantially reducing UAV flight distance and thereby improving overall exploration efficiency. What are the implications of the main findings? When acquiring any prior knowledge of unknown environments during autonomous exploration, the proposed algorithm can fully extract and leverage the structural information contained within it, thereby improving overall exploration efficiency. The autonomous exploration algorithm enables UAVs to complete exploration of unknown environments with shorter flight distances and durations, saving energy and allowing coverage of larger areas under battery-limited conditions. Autonomous exploration in unknown environments remains a challenging problem for UAVs. This paper proposes a hierarchical exploration planning framework that explicitly leverages real-time acquired prior knowledge to improve exploration efficiency. To efficiently represent the structural information embedded in the prior knowledge, two map structures, namely the quasi-prior map and the hybrid-topo map, are designed, enabling more reasonable space partition and facilitating exploration planning. Subsequently, based on the hybrid-topo map, the hierarchical exploration planner computes a global exploration guidance that provides an efficient traversal order over all unexplored regions. The local coverage problem in unknown regions is formulated as a coverage traveling salesman problem (CTSP), where visibility information derived from the hybrid-topo map is exploited to optimize local viewpoint sequences with high coverage efficiency. Finally, a long-horizon trajectory planning strategy is proposed to maintain high flight speed while ensuring safety and dynamic feasibility. Simulations demonstrate that the proposed framework significantly outperforms state-of-the-art exploration methods in terms of exploration efficiency, while ablation studies further validate the effectiveness of each module. Real-world experiments are conducted to confirm the practical capability of the proposed approach.